Method and system for automatically training machine learning model

Abstract

A method and system for automatically training a machine learning model is disclosed. The method performed by a computing device for automatically training a machine learning model includes the stepsof acquiring a data set including a plurality of data records; determining a feature engineering strategy for the data set through meta-learning; utilizing the determined feature engineering strategyto generate features related to each data record in the data set; constructing a machine learning sample based at least on the generated features; and training a machine learning model by using the constructed machine learning sample based on the automatically obtained hyper-parameter value.

Description

technical field [0001] The present application generally relates to the field of artificial intelligence, and more specifically, relates to a method and system for automatically training machine learning models. Background technique [0002] With the emergence of massive data, artificial intelligence technology has developed rapidly. In order to mine value from large amounts of data, relevant personnel not only need to be proficient in artificial intelligence technology (especially machine learning technology), but also need to be very familiar with the application of machine learning technology. Specific scenarios (for example, image processing, speech processing, text processing, and business decision-making fields such as automatic control, financial services, Internet advertising, etc.). For example, in machine learning, model training usually requires a large number of machine learning experts to participate in the work (including feature engineering strategy selection ...

AI Technical Summary

Problems solved by technology

For example, in machine learning, model training usually requires a large number of machine learning experts to participate in the work (including feature engineering strategy selection during training, model hyperparameter adjustment, etc.), and the effect of the trained model often depends on the machine learning experts. Personal experience about model training and their familiarity with the specific application scenarios of the model or related businesses, and if the relevant personnel do not know enough about the specific business or have insufficient modeling experience, it will easily lead to poor model effects

It can be seen that the existing model training methods will not only consume a lot of labor costs, but also lead to a high threshold for machine learning. In addition, due to the dependence on the personal experience and business familiarity of relevant personnel, the effect of the trained model may not be objective accurately reflect the real business rules, and these have brought great difficulties to the industrial application prospects of machine learning technology

Images